French Polynesia Road Surface and Passability Data for 600km of Arterial Roads

This dataset maps approximately 600 km of arterial roads in French Polynesia, providing AI-derived surface types and width classes generated by HeiGIT. It utilizes PlanetScope satellite imagery from 2020 and 2024 to classify motorway, trunk, primary, and secondary road segments. The data includes a Humanitarian Passability Index (HPI) to assess logistical accessibility across the island network.

Use Cases

• Assessing logistical accessibility for disaster response using the Humanitarian Passability Index (HPI) and Road Width Class
• Monitoring national infrastructure development by tracking transitions in the Road Surface Change column
• Enriching OpenStreetMap data by filling missing 'surface tag' values with 'DL Surface Prediction 2024' results

Strengths

• 89.2% surface model accuracy compared to 64.7% for standard OSM surface tags
• Multi-temporal coverage allowing for the detection of road surface changes between 2020 and 2024
• Standardized width classification (Class 1-3) based on heavy truck capacity and flow

Limitations

• Small geographic scale covering only 0.0006 million km of road network
• Potential for AI classification errors in areas with dense vegetation or cloud cover
• Focuses only on high-capacity arterial roads, omitting local connectivity

Provenance

Source

HeiGIT (Heidelberg Institute for Geoinformation Technology)

Collection Method

AI-derived predictions from PlanetScope satellite imagery integrated with OpenStreetMap road geometries

Time Range

2020-2024

Freshness

Last updated March 2026, with AI predictions derived from 2020 and 2024 satellite imagery.

Geography

French Polynesia